A method for operating a machine for producing and/or processing a material web, wherein a first drive unit is supplied by a converter with a current, a vibration propagating over the material web is captured via the first drive unit, the vibration is measured and transformed into a measurement signal that is examined for presence of a signature that differs from the basic waveform of the current, a web tear is thus identified if the signature propagating over the material web is missing during the evaluation of the electrical measurement signal, whereby no further sensors, in particular optical sensors, are required to capture the measurement signal, and the measurement also occurs independently of a torque, a speed or speed development of drive motors over time and, moreover, the detection of the web tear does not require a comparison measurement at the machine without a continuous material web.

Aspects of the present invention provide methods, systems, and/or the like for: (1) receiving first imaging data from a first imaging device, the first imaging data comprising infrared imaging data for at least a first portion of an article of manufacture during a manufacturing process; (2) deriving moisture profile data from the infrared imaging data the infrared imaging data; and (3) providing the moisture profile data to a quality control system for use in cross-direction and machine-direction control. In some aspects, the first imaging device may be placed in any suitable location along a papermaking or other manufacturing process to provide real-time, full-width moisture profiles of a paper web at any location in the process. They system may be utilized at papermaking startup and implemented to optimize paper machine dewatering on a component-by-component basis.

A system and method for labelling normal and abnormal regions in data related to a paper machine for web break prediction and labelling individual parameters for root cause analysis, using machine learning models, includes using the machine learning models in real-time to predict breaks in the paper web, analyzing root cause for the breaks in the paper web, and estimating a time to break. An auto-data-labeling framework helps in adaptive learning for autonomous model improvement of the deployed model, transfer learning, shortlisting parameters and automating feasibility study.

A system and method for labelling normal and abnormal regions in data related to a paper machine for web break prediction and labelling individual parameters for root cause analysis, using machine learning models, includes using the machine learning models in real-time to predict breaks in the paper web, analyzing root cause for the breaks in the paper web, and estimating a time to break. An auto-data-labeling framework helps in adaptive learning for autonomous model improvement of the deployed model, transfer learning, shortlisting parameters and automating feasibility study.

A method for monitoring an industrial plant. In a first part of the industrial plant, first parameters are provided. The industrial plant is used to produce and/or process a fibrous material web. Second parameters are provided in a second part. The parameters are stored, preferentially as time series. In the case of a web break in the second part, the second parameters are first analyzed for a second anomaly. If no second anomaly can be detected, the first parameters are analyzed for a first anomaly. During the analysis, the parameters which were stored in a time range before the web break are preferably examined. If a first or second anomaly is detected, these, and optionally measures to avoid such web breaks, are displayed to the user. Optionally, the first parameters and/or the second parameters can be set so as to avoid future web breaks.

A method for monitoring an industrial plant. In a first part of the industrial plant, first parameters are provided. The industrial plant is used to produce and/or process a fibrous material web. Second parameters are provided in a second part. The parameters are stored, preferentially as time series. In the case of a web break in the second part, the second parameters are first analyzed for a second anomaly. If no second anomaly can be detected, the first parameters are analyzed for a first anomaly. During the analysis, the parameters which were stored in a time range before the web break are preferably examined. If a first or second anomaly is detected, these, and optionally measures to avoid such web breaks, are displayed to the user. Optionally, the first parameters and/or the second parameters can be set so as to avoid future web breaks.